elizaos--eliza/.github/workflows/benchmark-weekly.yml

# Weekly EA + Connector Benchmark
#
# Runs the full executive-assistant and connector certification scenario
# catalogs through the live scenario runner and uploads a markdown + JSON
# benchmark report as an artifact. Scheduled/default dispatch runs are
# report-only so the weekly trend capture stays green while the live catalog
# is still being hardened; manual dispatch can opt into enforcement.
#
# Distinct from live-scenarios.yml: weekly cadence, emits a human-readable
# markdown report suitable for tracking trend lines over time.
#
# Required repo secrets (self-documented): identical to live-scenarios.yml.
#   LLM providers: OPENAI_API_KEY, OPENROUTER_API_KEY, ANTHROPIC_API_KEY,
#                  GOOGLE_GENERATIVE_AI_API_KEY, GOOGLE_API_KEY, GROQ_API_KEY
#   Google:  GOOGLE_OAUTH_CLIENT_ID, GOOGLE_OAUTH_CLIENT_SECRET,
#            GOOGLE_OAUTH_REFRESH_TOKEN, GMAIL_TEST_ACCOUNT_EMAIL,
#            GMAIL_TEST_ACCOUNT_REFRESH_TOKEN
#   Calendly: CALENDLY_API_TOKEN
#   Telegram: TELEGRAM_BOT_TOKEN, TELEGRAM_TEST_CHAT_ID, TELEGRAM_API_ID,
#             TELEGRAM_API_HASH
#   Discord:  DISCORD_BOT_TOKEN, DISCORD_TEST_GUILD_ID,
#             DISCORD_TEST_CHANNEL_ID
#   Signal:   SIGNAL_CLI_URL, SIGNAL_TEST_NUMBER
#   iMessage: IMESSAGE_BRIDGE_URL, IMESSAGE_TEST_HANDLE
#   WhatsApp: WHATSAPP_TOKEN, WHATSAPP_PHONE_ID, WHATSAPP_TEST_CONTACT
#   Twilio:   TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, TWILIO_FROM_NUMBER,
#             TWILIO_TEST_TO_NUMBER
#   X:        X_API_KEY, X_API_SECRET, X_ACCESS_TOKEN, X_ACCESS_SECRET,
#             X_TEST_DM_HANDLE
#   Push:     NOTIFICATION_RELAY_URL, NOTIFICATION_RELAY_TOKEN
#   Travel:   TRAVEL_BOOKING_API_KEY
# Optional:
#   LIFEOPS_JUDGE_THRESHOLD (workflow input, default 0.8)
#   SCENARIO_FILTER (workflow input, empty = all cataloged benchmark scenarios)
#   BENCHMARK_ENFORCE_GATE (workflow input, default false)

name: Benchmark (weekly)

on:
  schedule:
    # Mondays 10:00 UTC — after weekend regressions settle.
    - cron: "0 10 * * 1"
  workflow_dispatch:
    inputs:
      scenario_filter:
        description: "Comma-separated scenario ids (empty = full benchmark catalog)"
        required: false
        type: string
        default: ""
      judge_threshold:
        description: "LLM-judge minimum pass score (0.0 - 1.0)"
        required: false
        type: string
        default: "0.8"
      enforce_gate:
        description: "Fail the workflow when benchmark scenarios fail"
        required: false
        type: boolean
        default: false

concurrency:
  group: benchmark-weekly-${{ github.ref }}
  cancel-in-progress: false

env:
  BUN_VERSION: "canary"
  NODE_VERSION: "24.15.0"
  ELIZA_LIVE_TEST: "1"

permissions:
  contents: read
  actions: read

jobs:
  benchmark:
    name: EA + connector benchmark
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          fetch-depth: 0
          filter: blob:none
          submodules: recursive

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: ${{ env.NODE_VERSION }}

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: ${{ env.BUN_VERSION }}
          install-command: bun install --ignore-scripts --no-frozen-lockfile

      - name: Verify scenario-runner CLI present
        run: |
          test -f packages/scenario-runner/src/cli.ts || \
            { echo "scenario-runner CLI missing"; exit 1; }

      - name: Build benchmark runtime packages
        # The benchmark executes TypeScript sources directly, but several
        # workspace packages intentionally export dist/* entry points. Because
        # dependency installation ignores postinstall scripts, build only the
        # packages that the live scenario runtime imports through those exports.
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          GOOGLE_GENERATIVE_AI_API_KEY: ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
        run: |
          echo "::group::Build packages/core"
          bun run --cwd packages/core build
          echo "::endgroup::"

          echo "::group::Build packages/shared"
          # plugin-agent-skills (and others) consume @elizaos/shared via dist
          # exports (RouteRequestContext, route schemas). Must build before
          # any plugin that imports from it.
          bun run --cwd packages/shared build
          echo "::endgroup::"

          echo "::group::Build packages/skills"
          # plugin-agent-skills imports @elizaos/skills via its dist exports.
          bun run --cwd packages/skills build
          echo "::endgroup::"

          provider_package=""
          if [ -n "${GROQ_API_KEY:-}" ]; then
            provider_package="plugins/plugin-groq"
          elif [ -n "${OPENAI_API_KEY:-}" ]; then
            provider_package="plugins/plugin-openai"
          elif [ -n "${ANTHROPIC_API_KEY:-}" ]; then
            provider_package="plugins/plugin-anthropic"
          elif [ -n "${GOOGLE_GENERATIVE_AI_API_KEY:-}" ] || [ -n "${GOOGLE_API_KEY:-}" ]; then
            provider_package="plugins/plugin-google-genai"
          elif [ -n "${OPENROUTER_API_KEY:-}" ]; then
            provider_package="plugins/plugin-openrouter"
          fi

          package_dirs=(
            plugins/plugin-sql
            plugins/plugin-agent-skills
            plugins/plugin-pdf
            plugins/plugin-telegram
            plugins/plugin-whatsapp
            plugins/plugin-signal
            plugins/plugin-imessage
          )
          if [ -n "$provider_package" ]; then
            package_dirs+=("$provider_package")
          fi

          for package_dir in "${package_dirs[@]}"; do
            echo "::group::Build ${package_dir}"
            bun run --cwd "$package_dir" build
            echo "::endgroup::"
          done

      - name: Run benchmark harness
        id: run
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          GOOGLE_GENERATIVE_AI_API_KEY: ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
          GOOGLE_OAUTH_CLIENT_ID: ${{ secrets.GOOGLE_OAUTH_CLIENT_ID }}
          GOOGLE_OAUTH_CLIENT_SECRET: ${{ secrets.GOOGLE_OAUTH_CLIENT_SECRET }}
          GOOGLE_OAUTH_REFRESH_TOKEN: ${{ secrets.GOOGLE_OAUTH_REFRESH_TOKEN }}
          GMAIL_TEST_ACCOUNT_EMAIL: ${{ secrets.GMAIL_TEST_ACCOUNT_EMAIL }}
          GMAIL_TEST_ACCOUNT_REFRESH_TOKEN: ${{ secrets.GMAIL_TEST_ACCOUNT_REFRESH_TOKEN }}
          CALENDLY_API_TOKEN: ${{ secrets.CALENDLY_API_TOKEN }}
          TELEGRAM_BOT_TOKEN: ${{ secrets.TELEGRAM_BOT_TOKEN }}
          TELEGRAM_TEST_CHAT_ID: ${{ secrets.TELEGRAM_TEST_CHAT_ID }}
          TELEGRAM_API_ID: ${{ secrets.TELEGRAM_API_ID }}
          TELEGRAM_API_HASH: ${{ secrets.TELEGRAM_API_HASH }}
          DISCORD_BOT_TOKEN: ${{ secrets.DISCORD_BOT_TOKEN }}
          DISCORD_TEST_GUILD_ID: ${{ secrets.DISCORD_TEST_GUILD_ID }}
          DISCORD_TEST_CHANNEL_ID: ${{ secrets.DISCORD_TEST_CHANNEL_ID }}
          SIGNAL_CLI_URL: ${{ secrets.SIGNAL_CLI_URL }}
          SIGNAL_TEST_NUMBER: ${{ secrets.SIGNAL_TEST_NUMBER }}
          IMESSAGE_BRIDGE_URL: ${{ secrets.IMESSAGE_BRIDGE_URL }}
          IMESSAGE_TEST_HANDLE: ${{ secrets.IMESSAGE_TEST_HANDLE }}
          WHATSAPP_TOKEN: ${{ secrets.WHATSAPP_TOKEN }}
          WHATSAPP_PHONE_ID: ${{ secrets.WHATSAPP_PHONE_ID }}
          WHATSAPP_TEST_CONTACT: ${{ secrets.WHATSAPP_TEST_CONTACT }}
          TWILIO_ACCOUNT_SID: ${{ secrets.TWILIO_ACCOUNT_SID }}
          TWILIO_AUTH_TOKEN: ${{ secrets.TWILIO_AUTH_TOKEN }}
          TWILIO_FROM_NUMBER: ${{ secrets.TWILIO_FROM_NUMBER }}
          TWILIO_TEST_TO_NUMBER: ${{ secrets.TWILIO_TEST_TO_NUMBER }}
          X_API_KEY: ${{ secrets.X_API_KEY }}
          X_API_SECRET: ${{ secrets.X_API_SECRET }}
          X_ACCESS_TOKEN: ${{ secrets.X_ACCESS_TOKEN }}
          X_ACCESS_SECRET: ${{ secrets.X_ACCESS_SECRET }}
          X_TEST_DM_HANDLE: ${{ secrets.X_TEST_DM_HANDLE }}
          NOTIFICATION_RELAY_URL: ${{ secrets.NOTIFICATION_RELAY_URL }}
          NOTIFICATION_RELAY_TOKEN: ${{ secrets.NOTIFICATION_RELAY_TOKEN }}
          TRAVEL_BOOKING_API_KEY: ${{ secrets.TRAVEL_BOOKING_API_KEY }}
          SCENARIO_FILTER: ${{ inputs.scenario_filter }}
          LIFEOPS_JUDGE_THRESHOLD: ${{ inputs.judge_threshold || '0.8' }}
          BENCHMARK_ENFORCE_GATE: ${{ inputs.enforce_gate && '1' || '0' }}
          BENCHMARK_REPORT_PATH: artifacts/benchmark-report.md
        # Trajectory data and ephemeral state land under ~/.eliza per
        # eliza-native ELIZA_STATE_DIR convention.
        run: node packages/scripts/run-scenario-benchmark.mjs

      - name: Upload benchmark report
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a
        with:
          name: benchmark-report
          path: |
            artifacts/benchmark-report.md
            artifacts/lifeops-scenario-report.json
          if-no-files-found: warn
          retention-days: 90